A 3D facial motion tracking approach has been proposed based on the incorporation of online appearance model (OAM) and cylinder head model (CHM) in the framework of particle filtering. 1) For the construction of OAM, multi-measurements are infused to reduce the influence of lighting and person dependence. 2) The global motion acquired from CHM fitting is set as the initialization of OAM fitting, and the fitting result is set as the initialization of CHM in the next frame. 3) Motion filtering is applied with particle filter combined with local optimization and improved resampling. Objective between subjects evaluations show that our approach is fit to track facial motions.